© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34774
    Prev
    Next
    INDEX
    Explanations

    nationalist uprising or political opponent

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron strongly activates on proper names (especially political figures and organizations) and on numeric tokens (years, numbers), i.e. named entities and numeric references.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gradually
    -1.03
     until
    -1.02
     berbagai
    -0.98
    Eventually
    -0.94
    러나
    -0.94
    drawn
    -0.91
    ₁(
    -0.89
    URLEncoder
    -0.88
    terus
    -0.88
    ˃
    -0.88
    POSITIVE LOGITS
     this
    1.00
    這次
    1.00
     was
    0.98
    这次
    0.96
     vanligt
    0.87
    又一次
    0.85
     Đó
    0.85
    はこの
    0.84
     đây
    0.84
     очеред
    0.84
    Activations Density 0.074%

    No Known Activations